A wind turbine yaw fault diagnosis method based on ternary data mutation coupling

Abstract

The application relates to a yaw fault diagnosis method for a wind turbine based on three-element data mutation coupling, wherein the method comprises the following steps: acquiring three-element yaw monitoring parameters in a preset time period, the three-element yaw monitoring parameters comprising a yaw rotation rate, a yaw motor current and a yaw pressure pulsation; determining a three-element abnormal value interval according to the standard deviation of the change rate of each yaw monitoring parameter, and determining an abnormal value of each yaw monitoring parameter based on the values of adjacent monitoring moments in the three-element abnormal value interval; judging whether the abnormal value is mutation data according to a preset mutation threshold, and coupling the three-element abnormal values at the same moment according to the judgment result to obtain a coupled target abnormal state code; acquiring a mapping relationship among abnormal state codes, diagnosis bases and fault types, and determining a target diagnosis base and a target fault type corresponding to the target abnormal state code from the mapping relationship.

Description

TECHNICAL FIELD

[0001] The present application relates to the yaw fault diagnosis field, in particular to a wind turbine yaw fault diagnosis method based on three-element data mutation coupling. BACKGROUND

[0002] The yaw system is the core subsystem of the wind turbine, responsible for adjusting the orientation of the nacelle to maximize the capture of wind energy, and its reliability directly affects the power generation efficiency and equipment safety. Frequent yaw system failures can cause power loss, and the maintenance cost accounts for 10%-30% of the income of the wind farm, and may cause a chain of structural damage. The yaw system fault type and cause complexity, yaw fault has multi-source and mutation, fault types include (1) mechanical faults: gear and bearing failure; gear tooth breakage (due to insufficient lubrication or assembly stress); bearing raceway spalling (long-term overload or corrosion). Abnormal brake system: brake force is insufficient due to hydraulic caliper oil leakage, causing nacelle slip and impact load. (2) Electrical and control faults: sensor distortion, wind vane disturbed by blade wake, measurement error > 3°, power generation decreases by 2.1%. Control logic defects: yaw motor frequent start-stop aggravates vibration, triggers acceleration overrun shutdown. (3) Environmental coupling mutation; dynamic load mutation, yaw drive torque fluctuation reaches 30% of the rated value under turbulent wind conditions, inducing gear overload. Lubrication state mutation, low temperature causes lubricating grease hardening, gear dry friction causes abnormal noise and wear.

[0003] The prior art relies on a single state signal, and has the problems of low fault diagnosis accuracy and inability to accurately determine the specific cause of the yaw anomaly. SUMMARY

[0004] The embodiments of the present application provide a wind turbine yaw fault diagnosis method based on three-element data mutation coupling, to at least solve the problem of low fault diagnosis accuracy and inability to accurately determine the specific cause of the yaw anomaly in related technologies.

[0005] In a first aspect, the embodiments of the present application provide a wind turbine yaw fault diagnosis method based on three-element data mutation coupling, comprising:

[0006] Obtaining three-element yaw monitoring parameters in a preset time period, the three-element yaw monitoring parameters including yaw rotation rate, yaw motor current and yaw pressure pulsation;

[0007] Determining a three-element abnormal value interval according to the standard deviation of the change rate of each yaw monitoring parameter, and determining the abnormal value of each yaw monitoring parameter based on the values of adjacent monitoring time points in the three-element abnormal value interval;

[0008] determining whether the abnormal value is mutation data according to a preset mutation threshold, and coupling the three abnormal values at the same time according to a result of the determination to obtain a target abnormal state code after coupling;

[0009] obtaining a mapping relationship between the abnormal state code, a diagnosis basis and a fault type, and determining a target diagnosis basis and a target fault type corresponding to the target abnormal state code from the mapping relationship according to the target abnormal state code.

[0010] In an embodiment, the determination of the three abnormal value intervals according to the standard deviation of the change rate of each yaw monitoring parameter comprises:

[0011] calculating the change rate of each yaw monitoring parameter at the current time and the previous time;

[0012] calculating the standard deviation of the change rate of each yaw monitoring parameter from the start time to the current time;

[0013] in a preset time period, in response to the absolute value of the change rate being greater than three times the standard deviation of the corresponding yaw monitoring parameter, adding the multi-yaw monitoring parameter at the corresponding time to the three abnormal value intervals.

[0014] In an embodiment, the determination of the abnormal value of each yaw monitoring parameter based on the values of adjacent monitoring times in the three abnormal value intervals comprises:

[0015] determining whether the average of the values of two adjacent monitoring times of each yaw monitoring parameter in the three abnormal value intervals is greater than a preset average value, or whether the difference between the values of two adjacent monitoring times is greater than a preset difference value;

[0016] if yes, the monitoring value at the current monitoring time is taken as the abnormal value of the corresponding yaw monitoring parameter.

[0017] In an embodiment, the coupling of the three abnormal values at the same time according to the result of the determination to obtain the target abnormal state code after coupling comprises:

[0018] the abnormal value is marked with a first identifier for mutation data and a second identifier for non-mutation data, and the target abnormal state code is determined according to the first identifier and the second identifier.

[0019] In an embodiment, the mapping relationship between the abnormal state code and the fault type comprises:

[0020] when the yaw pressure pulsation is mutation data, and the yaw rotation rate and the yaw motor current are mutation data, the fault type is hydraulic system failure or motor system failure;

[0021] when the yaw pressure pulsation is non-sudden data, and the yaw rotation rate and the yaw motor current are sudden data, the fault type is yaw gear tooth breakage or soft starter failure;

[0022] when the yaw pressure pulsation is sudden data, and the yaw rotation rate is non-sudden data, and the yaw motor current is sudden data, the fault type is yaw resonance.

[0023] In an embodiment, in response to the target fault type corresponding to the target abnormal state code being more than one, the method further comprises:

[0024] determining the order in which the yaw monitoring parameters appear sudden according to the abnormal values of adjacent monitoring time points;

[0025] if the yaw pressure pulsation appears sudden earliest, and the yaw rotation rate and the yaw motor current are both sudden data, the fault type is hydraulic system failure;

[0026] if the motor current appears sudden earliest, and the yaw rotation rate and the yaw motor current are both sudden data, the fault type is motor system failure;

[0027] if the yaw rotation rate appears sudden earliest, and the yaw pressure pulsation is non-sudden data, and the yaw motor current is sudden data, the fault type is yaw gear tooth breakage.

[0028] In a second aspect, the embodiments of the present application provide a wind turbine yaw fault diagnosis system based on three-element data sudden coupling, comprising:

[0029] an acquisition module: configured to acquire three-element yaw monitoring parameters in a preset time period, the three-element yaw monitoring parameters comprising a yaw rotation rate, a yaw motor current and a yaw pressure pulsation;

[0030] an abnormality module: configured to determine a three-element abnormal value interval according to the standard deviation of the change rate of each yaw monitoring parameter, and determine an abnormal value of each yaw monitoring parameter based on the values of adjacent monitoring time points in the three-element abnormal value interval;

[0031] a state code module: configured to determine whether the abnormal value is sudden data according to a preset sudden threshold, and couple the three-element abnormal values at the same time point according to the determination result to obtain a target abnormal state code after coupling;

[0032] a diagnosis module: configured to acquire a mapping relationship among an abnormal state code, a diagnosis basis and a fault type, and determine a target diagnosis basis and a target fault type corresponding to the target abnormal state code from the mapping relationship.

[0033] In a third aspect, the embodiments of the present application provide a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the method for yaw fault diagnosis of a wind turbine based on mutation coupling of ternary data according to the first aspect.

[0034] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program executable by a processor, and the computer program implements the method for yaw fault diagnosis of a wind turbine based on mutation coupling of ternary data according to the first aspect.

[0035] The method for yaw fault diagnosis of a wind turbine based on mutation coupling of ternary data provided by the embodiments of the present application has at least the following technical effects.

[0036] The embodiments of the present application gradually locate abnormal data from the monitoring data by analyzing the change rate of yaw rotation rate, yaw motor current and yaw pressure fluctuation and monitoring quantity. The mutation data is screened and determined by a preset mutation threshold, and the abnormal data is further screened, which is beneficial to accurately determine the mutation data, and then the yaw motor current, yaw hydraulic pressure and yaw rate are coupled to determine the target abnormal state code, so as to determine the fault type according to the target abnormal state code. The embodiments of the present application comprehensively utilize the characteristics of ternary monitoring data, and improve the accuracy of fault diagnosis. The problem of insufficient fault diagnosis accuracy caused by relying on a single state signal in the current yaw system diagnosis process is solved, and the specific reason for yaw abnormality can be accurately obtained.

[0037] The details of one or more embodiments of the present application are presented in the following drawings and description to make other features, objects and advantages of the present application more apparent. BRIEF DESCRIPTION OF DRAWINGS

[0038] The drawings described herein are intended to provide further understanding of the present application, and form a part of the present application. The illustrative embodiments of the present application and their description serve to explain the present application, and do not constitute an improper limitation of the present application. In the drawings:

[0039] Figure 1 is a flowchart of a method for yaw fault diagnosis of a wind turbine based on mutation coupling of ternary data according to an embodiment of the present application;

[0040] Figure 2 is a method for generating a target abnormal state code according to an exemplary embodiment;

[0041] Figure 3 is a structural block diagram of a system for yaw fault diagnosis of a wind turbine based on mutation coupling of ternary data according to an embodiment of the present application;

[0042] Figure 4 A structural schematic diagram of an electronic device is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application is described and explained below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0044] Obviously, the drawings in the following description are only some examples or embodiments of the present application, and for those of ordinary skill in the art, the present application can be applied to other similar scenarios without creative efforts based on these drawings. In addition, it can be understood that although the efforts made in this development process can be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some design, manufacture or production changes based on the technical content disclosed in the present application are only routine technical means and should not be understood as insufficient disclosure of the content disclosed in the present application.

[0045] In the present application, the phrase "embodiments" means that the specific features, structures or properties described in combination with the embodiments can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor is it an independent or alternative embodiment to other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in the present application can be combined with other embodiments without conflict.

[0046] Unless otherwise defined, technical terms and scientific terms used in the present application shall have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. Unless otherwise defined, the terms "one" and "a" or "an" used in the present application shall not be limited to singular aspects but can include both singular and plural aspects. The terms "comprising," "including," "containing," and any variations thereof in the present application shall be taken to cover both cases where one or more steps or modules (units) are included in the process, method, system, product, or apparatus and cases where one or more steps or modules (units) are not included in the process, method, system, product, or apparatus. The terms "connected," "coupled," and similar terms in the present application shall not be limited to physical or mechanical connections but can include electrical connections, whether direct or indirect. The term "plurality" in the present application refers to two or more. The term "and / or" describes the associated relationship of the associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that A exists alone, A and B exist together, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects. The terms "first," "second," "third," and the like in the present application are merely to distinguish similar objects and do not represent a specific order for the objects.

[0047] In a first aspect, the embodiments of the present application provide a yaw fault diagnosis method for a wind turbine based on three-element data mutation coupling, Figure 1 is a flowchart of a yaw fault diagnosis method for a wind turbine based on three-element data mutation coupling according to an embodiment of the present application, as Figure 1 shown, the method comprises:

[0048] In step S101, three-element yaw monitoring parameters in a preset time period are acquired, the three-element yaw monitoring parameters comprising a yaw rotation rate, a yaw motor current, and a yaw pressure pulsation.

[0049] Optionally, the preset time interval can be set according to actual needs, such as 0.5 min, 1 min, etc. For ease of observation and calculation, it is usually set to 1 minute. The three-dimensional yaw monitoring parameters include yaw rotation rate (m / s), yaw motor current (A), and yaw pressure pulsation (bar). Generally speaking, the larger the dimension of the yaw monitoring parameters, the higher the corresponding diagnostic accuracy. Among them, yaw pressure pulsation data is acquired in real time by a pressure sensor and is used to monitor the pressure of the yaw hydraulic system (such as yaw residual pressure). Yaw rotation rate data is acquired through an encoder or pulse signal; yaw speed (unit: degrees / second) is used to detect sudden rate changes during yaw start / braking (such as soft start failure causing the speed to drop to zero). Yaw motor current data is recorded by a yaw motor current relay to determine whether the yaw motor current exceeds the protection setting.

[0050] In this way, multiple monitoring parameters such as yaw rotation rate, yaw motor current and yaw pressure pulsation can be obtained. By comprehensively utilizing the characteristics of multiple monitoring data, it is beneficial to improve the accuracy of subsequent fault diagnosis.

[0051] Step S102: Determine the three-dimensional abnormal value interval based on the standard deviation of the rate of change of each yaw monitoring parameter, and determine the abnormal value of each yaw monitoring parameter based on the values ​​of adjacent monitoring times in the three-dimensional abnormal value interval.

[0052] Optionally, by analyzing the rate of change, amount of change, and monitored quantities of yaw rotation rate, yaw motor current, and yaw pressure pulsation, abnormal values ​​among the monitored parameters can be gradually screened out. This facilitates the accurate identification of abnormal data, which is beneficial for subsequent fault diagnosis based on precise abnormal data, thereby improving the accuracy of fault diagnosis.

[0053] In one example, step S102 includes:

[0054] Step S1021: Calculate the rate of change of each yaw monitoring parameter between the current time and the previous time.

[0055] Step S1022: Calculate the standard deviation of the rate of change of each yaw monitoring parameter from the start time to the current time.

[0056] Step S1023: Within a preset time period, if the absolute value of the rate of change is greater than three times the standard deviation of the corresponding yaw monitoring parameter, the multivariate yaw monitoring parameter at the corresponding time is added to the ternary abnormal value range.

[0057] Optionally, assuming a preset time period of 1 minute, the numerical range of any one of the following within 1 minute—yaw rotation rate, yaw motor current, and yaw pressure pulsation—can be expressed as {x} i For each element (i=1,2,…,n), the following steps can be used to filter out the range of ternary abnormal values.

[0058] calculating a change rate Δx of the observation quantity at the current observation time and the previous observation time i calculating a change rate standard deviation s of the observation time sequence at the current i time i judging the size of the change rate |Δx i | and 3s i , if |Δx i | > 3s i , x i is an abnormal observation point, and the monitoring data corresponding to the x i time is added to the abnormal value interval; otherwise, x i is a normal observation point. If x i is a normal observation point, the observation value at the next time is continuously judged until all abnormal observation points in the current time period are screened out.

[0059] In one example, step S102 includes: judging whether the average value of the values of each yaw monitoring parameter at two adjacent monitoring times in the ternary abnormal value interval is greater than a preset average value, or whether the difference value of the values of two adjacent monitoring times is greater than a preset difference value. If yes, the monitoring value at the current monitoring time is taken as the abnormal value of the corresponding yaw monitoring parameter.

[0060] Optionally, the preset difference value and the preset average value can be set according to the actual application scene. In the ternary abnormal value interval, for any one of the yaw rotation rate, the yaw motor current and the yaw pressure pulsation, it is judged whether the difference value of the monitoring data at the current monitoring time and the previous monitoring time is greater than the preset difference value, if yes, the monitoring value at the current time is taken as the abnormal value of the corresponding yaw monitoring parameter. Or, it is judged whether the average value of the monitoring data at the current monitoring time and the previous monitoring time is greater than the preset average value, if yes, the monitoring value at the current time is taken as the abnormal value of the corresponding yaw monitoring parameter. In this way, the abnormal data is accurately located from the monitoring data, which is beneficial to fault diagnosis according to the accurate abnormal data, thereby improving the accuracy of fault diagnosis.

[0061] Step S103, judging whether the abnormal value is mutation data according to a preset mutation threshold, and coupling the ternary abnormal values at the same time according to the judgment result to obtain a coupled target abnormal state code.

[0062] Optionally, the preset mutation threshold includes a pressure mutation threshold, a rate mutation threshold and a motor current threshold, wherein the mutation threshold can be set according to the actual operation of the unit, and is not limited to the examples listed in the application. The current mutation threshold can be a current value or a current variance. The mutation data and the non-mutation data are differentially identified, and the identification results of the three parameters are coupled to obtain the target abnormal state code.

[0063] The preset mutation threshold can be set according to actual conditions, for example, the pressure mutation threshold is set to a range of ±10 bar of the operating pressure and ±15 bar of the stopping pressure, and when the yaw pressure pulsation is outside the pressure mutation threshold, it is mutation data; the rate mutation threshold is set to a yaw speed deviation from the command value > 0.2 degrees / second as mutation data; and the yaw motor current threshold is set to 9.5 A, and the current value > 9.5 A in the yaw state. The multi-element mutation interval can also be determined according to the motor current variance, which can be set according to actual conditions. For example, the non-yaw state is set to a current variance < 0.5, and the yaw state is set to a variance > 2.0.

[0064] In this way, by presetting the mutation threshold to screen and determine the mutation data, the abnormal data is further screened, which is beneficial to accurately determine the mutation data, and then the three-element parameters are coupled to determine the target abnormal state code, so as to determine the fault type according to the mutation data and the mutation state. And the abnormal state code represents whether the parameter is abnormal, and the multi-element monitoring data features are comprehensively utilized, which is beneficial to improve the accuracy of subsequent fault diagnosis.

[0065] In one example, step S103 includes: marking mutation data with a first identifier and marking non-mutation data with a second identifier, and determining a target abnormal state code according to the first identifier and the second identifier.

[0066] Optionally, Figure 2 is a target abnormal state code generation method according to an example embodiment. As shown in Figure 2 The first identifier and the second identifier can be set according to actual needs. In this application, the first identifier and the second identifier are 0 and 1 respectively. For example, the pressure mutation threshold range is ±10 bar of the operating pressure and ±15 bar of the stopping pressure, and when it is within the threshold range, the identifier is 1; and when it is outside the threshold range, the identifier is 0. The rate mutation threshold is set to a yaw speed deviation from the command value > 0.2 degrees / second, and the identifier within the threshold range is 1, and the identifier outside the threshold range is 0. The identifier within the threshold range is 1, and the identifier outside the threshold range is 0. The yaw motor current threshold is set to a yaw state variance > 2.0. The identifier within the threshold range is 1, and the identifier outside the threshold range is 0. Among them, 1 identifies mutation data, and 0 represents normal data. In this way, the three-element data state is marked by the identifier, and whether the data is marked, which is beneficial to coupling the three-element data, so as to directly determine the fault type according to the coupling result.

[0067] Step S104, obtaining a mapping relationship between the abnormal state code, the diagnosis basis and the fault type, and determining the target diagnosis basis and the target fault type corresponding to the target abnormal state code from the mapping relationship

[0068] Optionally, the abnormal state code can be set according to actual needs, and the mapping relationship between the abnormal state code, the diagnosis basis and the fault type is pre-acquired, and the specific basis is derived according to historical experience and related field knowledge.

[0069] In one example, the mapping relationship between the abnormal state code and the fault type includes:

[0070] When the yaw pressure pulsation is sudden data, and the yaw rotation rate and the yaw motor current are sudden data, the fault type is hydraulic system failure or motor system failure.

[0071] When the yaw pressure pulsation is non-sudden data, and the yaw rotation rate and the yaw motor current are sudden data, the fault type is yaw gear tooth breakage or soft starter failure.

[0072] When the yaw pressure pulsation is sudden data, and the yaw rotation rate is non-sudden data, and the yaw motor current is sudden data, the fault type is yaw resonance.

[0073] Optionally, Table 1 is a mapping table of the abnormal state code, the diagnosis basis and the fault type.

[0074] Table 1

[0075] Fault Type Yaw Pressure Surge Characteristics Yaw Rate Characteristics Yaw Motor Current Characteristics Diagnosis Basis Hydraulic System Failure 1 Pressure consistently below setpoint 1 Rate fluctuation large or zeroed out 1 Current mean normal, variance spikes (current spikes) Pressure vs. rate mismatch Yaw gear tooth breakage 0 Pressure normal 1 Rate jump (encoder anomaly) 1 Current variance > 3.0 and current spikes Current vs. rate anomaly coupling Soft starter failure 0 Pressure normal 1 Rate zeroed out 1 Current mean > 1.5 (motor overload) Rate zeroed out with current imbalance Yaw resonance 1 Excess pressure median out of limits 0 Rate normal 1 Variance > 2.5 (tower / cap system excitation) Current vs. pressure anomaly coupling

[0076] As shown in Table 1, the corresponding fault type and diagnosis basis can be determined according to the state code of the ternary yaw monitoring parameter. For example, the fault reason of pressure sudden + rate zero may be hydraulic system blockage; the fault reason of pressure and current synchronous overrun may be yaw brake system jamming or resonance. As an example, when the abnormal state code is 111, the corresponding fault type is hydraulic system failure, and the corresponding diagnosis basis is pressure and rate mismatch; when the abnormal state code is 011, the corresponding fault type is yaw gear tooth breakage or soft starter failure, and the corresponding diagnosis basis is current and rate abnormal coupling or rate zero with current imbalance; when the abnormal state code is 101, the corresponding fault type is yaw resonance, and the corresponding diagnosis basis is current and pressure synchronous overrun.

[0077] In addition, the fault reason is also related to the abnormal order of the yaw motor current, the yaw hydraulic pressure and the yaw rate. For example, when the abnormal state code is 111, the corresponding fault type may also be motor system failure. For the case where there are two fault types corresponding to the abnormal state code, when the target abnormal state code is the same, an additional judgment condition is set to further accurately judge the fault type, and the specific reason of the yaw abnormality can be accurately obtained.

[0078] In this way, the yaw motor current, yaw hydraulic pressure, yaw speed three-state data are coupled, the multi-dimensional feature information and the judgment criteria are fully utilized, and the yaw fault diagnosis is performed. The problem of insufficient fault diagnosis precision caused by relying on a single state signal in the current yaw system diagnosis process is solved.

[0079] In one example, in response to the target fault type corresponding to the target abnormal state code being more than one, the method further includes:

[0080] The order in which the yaw monitoring parameters appear mutations is determined according to the abnormal values of adjacent monitoring moments.

[0081] If the yaw pressure pulsation appears the earliest mutation, and the yaw rotation rate and the yaw motor current are both mutation data, the fault type is hydraulic system failure.

[0082] If the motor current appears the earliest mutation, and the yaw rotation rate and the yaw motor current are both mutation data, the fault type is motor system failure.

[0083] If the yaw rotation rate appears the earliest mutation, and the yaw pressure pulsation is non-mutation data, and the yaw motor current is mutation data, the fault type is yaw gear tooth breakage.

[0084] Optionally, the order in which the yaw monitoring parameters appear mutations is determined according to the abnormal values of adjacent monitoring moments. For example, only the yaw pressure pulsation appears mutation at the last moment, and the pressure, the yaw rotation rate and the yaw motor current all appear mutation at the current moment, so the yaw pressure pulsation appears the earliest mutation. Further, assuming that the abnormal state code is 111, the corresponding fault type can be motor system failure or hydraulic system failure. If the yaw pressure pulsation appears the earliest mutation, the fault type is hydraulic system failure, and the diagnosis basis is pressure and rate mismatch. If the motor current appears the earliest mutation, the fault type is motor system failure. Assuming that the abnormal state code is 011, the corresponding fault type is yaw gear tooth breakage or soft starter failure. If the yaw rotation rate appears the earliest mutation, the corresponding fault type is yaw gear tooth breakage, and the diagnosis basis is current and rate abnormal coupling.

[0085] In some embodiments, the final fault type and the final diagnosis basis can also be determined from the target fault type according to the mean value, the variance, the yaw rotation rate and the preset judgment threshold.

[0086] Optionally, continuing to refer to Table 1, when the abnormal state code is 011, the corresponding fault type is yaw gear tooth breakage or soft starter failure, at this time, the mean and variance of the yaw motor current at the current time and the last time are needed to further accurately determine the final fault type. When the current variance is > 3.0, the corresponding fault type is yaw gear tooth breakage, and the corresponding diagnosis basis is current and speed abnormal coupling; when the current mean is > 1.5, the corresponding fault type is soft starter failure, and the corresponding diagnosis basis is speed zeroing with current imbalance. Alternatively, further judgment can also be made according to the yaw rotation rate, when the yaw rotation rate is zero, the corresponding fault type is soft starter failure, and the corresponding diagnosis basis is speed zeroing with current imbalance. Otherwise, the corresponding fault type is yaw gear tooth breakage, and the corresponding diagnosis basis is current and speed abnormal coupling.

[0087] In this way, when the abnormal state code is consistent, additional judgment conditions are set to further accurately determine the fault type, improving the accuracy of fault diagnosis, and the specific reason for the yaw abnormality can be accurately determined.

[0088] In summary, the present application gradually locates abnormal data from monitoring data by analyzing the yaw rotation rate, yaw motor current, and change rate and change amount of yaw pressure pulsation, which is beneficial to fault diagnosis according to accurate abnormal data, thereby improving the accuracy of fault diagnosis. By presetting a mutation threshold to cooperatively select and determine mutation data, the mutation data is further selected, which is beneficial to accurately determining the mutation data, and then coupling the yaw motor current, yaw hydraulic pressure, and yaw speed three parameters to determine the target abnormal state code, thereby determining the fault type according to the mutation data and mutation state. The present application comprehensively utilizes the characteristics of multiple monitoring data to improve the accuracy of fault diagnosis. The problem of insufficient fault diagnosis accuracy caused by relying on a single state signal in the current yaw system diagnosis process is solved. And when the abnormal state code is consistent, additional judgment conditions are set to further accurately determine the fault type, improving the accuracy of fault diagnosis, and the specific reason for the yaw abnormality can be accurately determined.

[0089] In a second aspect, the embodiments of the present application provide a wind turbine yaw fault diagnosis system based on three-element data mutation coupling, Figure 3 is a structural block diagram of a wind turbine yaw fault diagnosis system based on three-element data mutation coupling according to the embodiments of the present application, as Figure 3 shown, the system comprises:

[0090] The acquisition module 100 is used to acquire three-element yaw monitoring parameters in a preset time period, and the three-element yaw monitoring parameters include a yaw rotation rate, a yaw motor current, and a yaw pressure pulsation.

[0091] The abnormality module 200 is configured to determine a three-element abnormality numerical interval according to a standard deviation of a change rate of each yaw monitoring parameter, and determine an abnormality value of each yaw monitoring parameter based on a value of adjacent monitoring time in the three-element abnormality numerical interval.

[0092] The state code module 300 is configured to determine whether the abnormality value is mutation data according to a preset mutation threshold, and couple the three-element abnormality values at the same time according to a determination result to obtain a coupled target abnormality state code.

[0093] The diagnosis module 400 is configured to obtain a mapping relationship between the abnormality state code, a diagnosis basis and a fault type, and determine a target diagnosis basis and a target fault type corresponding to the target abnormality state code from the mapping relationship.

[0094] In one example, the abnormality module 200 includes a unit configured to calculate a change rate of each yaw monitoring parameter at a current time and a previous time, calculate a standard deviation of a change rate of each yaw monitoring parameter from a start time to a current time, and add a multi-element yaw monitoring parameter at a corresponding time to a three-element abnormality numerical interval in response to an absolute value of the change rate being greater than three times a standard deviation of the corresponding yaw monitoring parameter within a preset time period.

[0095] In one example, the abnormality module 200 includes a unit configured to determine whether an average value of values of two adjacent monitoring times of each yaw monitoring parameter in the three-element abnormality numerical interval is greater than a preset average value, or a difference value of the values of the two adjacent monitoring times is greater than a preset difference value. If yes, a monitoring value at a current monitoring time is taken as an abnormality value of the corresponding yaw monitoring parameter.

[0096] In one example, the state code module 300 includes a unit configured to mark mutation data with a first identifier and non-mutation data with a second identifier, and determine a target abnormality state code according to the first identifier and the second identifier.

[0097] In one example, the mapping relationship between the abnormality state code and the fault type in the diagnosis module 400 includes:

[0098] When the yaw pressure pulsation is mutation data, and the yaw rotation rate and the yaw motor current are mutation data, the fault type is hydraulic system failure or motor system failure.

[0099] When the yaw pressure pulsation is non-mutation data, and the yaw rotation rate and the yaw motor current are mutation data, the fault type is yaw gear tooth breakage or soft starter failure.

[0100] When the yaw pressure pulsation is mutation data, and the yaw rotation rate is non-mutation data, and the yaw motor current is mutation data, the fault type is yaw resonance.

[0101] In one example, in response to the target fault type corresponding to the target abnormal state code being more than one, the method further comprises:

[0102] A sequence for determining a yaw monitoring parameter mutation according to abnormal values of adjacent monitoring moments.

[0103] If the yaw pressure pulsation is the earliest to mutate, and both the yaw rotation rate and the yaw motor current are mutation data, the fault type is hydraulic system failure;

[0104] If the motor current is the earliest to mutate, and both the yaw rotation rate and the yaw motor current are mutation data, the fault type is motor system failure.

[0105] If the yaw rotation rate is the earliest to mutate, and the yaw pressure pulsation is non-mutation data, and the yaw motor current is mutation data, the fault type is yaw gear tooth breakage.

[0106] In summary, the present application gradually locates abnormal data from monitoring data by analyzing the change rate, change amount and monitoring amount of the yaw rotation rate, yaw motor current and yaw pressure pulsation, which is beneficial to fault diagnosis according to accurate abnormal data, thereby improving the accuracy of fault diagnosis. By presetting a mutation threshold to cooperatively screen and determine mutation data, the abnormal data is further screened, which is beneficial to accurately determining mutation data, and then coupling the yaw motor current, yaw hydraulic pressure and yaw rotation rate three parameters to determine a target abnormal state code, thereby determining a fault type according to mutation data and mutation state. The present application comprehensively utilizes multiple monitoring data characteristics to improve the accuracy of fault diagnosis. The problem of insufficient fault diagnosis accuracy caused by relying on a single state signal in the current yaw system diagnosis process is solved. In addition, when the abnormal state code is consistent, an additional judgment condition is set to further accurately judge the fault type, thereby improving the accuracy of fault diagnosis and accurately obtaining the specific reason for yaw abnormality.

[0107] In a third aspect, an electronic device is provided, Figure 4 A structural schematic diagram of an electronic device provided by the present application. The electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the program to implement the wind turbine yaw fault diagnosis method based on three-element data mutation coupling provided in the first aspect, Figure 4 The electronic device 60 shown is merely an example and should not limit the functions and use range of the present application.

[0108] The electronic device 60 can be in the form of a general computing device, for example, it can be a server device. The components of the electronic device 60 can include, but are not limited to, the at least one processor 61 described above, the at least one memory 62 described above, and a bus 63 connecting different system components, including the memory 62 and the processor 61.

[0109] The bus 63 includes a data bus, an address bus, and a control bus.

[0110] The memory 62 can include volatile memory, such as random access memory (RAM) 621 and / or cache memory 622, and can further include non-volatile memory, such as read-only memory (ROM) 623.

[0111] The memory 62 can further include a program / utility 625 having a set (at least one) of program modules 624, including but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which can include implementation of a network environment, individually or in some combination.

[0112] The processor 61 performs various function applications and data processing by running the computer program stored in the memory 62, such as the wind turbine yaw fault diagnosis method based on ternary data mutation coupling provided in the first aspect of the present application.

[0113] The electronic device 60 can also communicate with one or more external devices 64 (such as a keyboard or a pointing device, etc.) through an input / output (I / O) interface 65. Furthermore, the model generation electronic device 60 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 66. As shown, the network adapter 66 communicates with other modules of the model generation electronic device 60 through the bus 63. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in conjunction with the model generation electronic device 60, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID (Redundant Array of Independent Disks) systems, tape drives, and data backup storage systems, etc.

[0114] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, such division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules for embodiment.

[0115] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a program. The program is executed by a processor to implement the method for diagnosing yaw fault of a wind turbine generator based on ternary data mutation coupling according to the first aspect.

[0116] More specifically, the readable storage medium can include, but is not limited to, a portable disc, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0117] In possible implementation manners, the present application can also be implemented in the form of a program product, which includes program codes for causing a terminal device to perform the steps of the method for diagnosing yaw fault of a wind turbine generator based on ternary data mutation coupling according to the first aspect when the program product is run on the terminal device.

[0118] The program codes for executing the present application can be written in any combination of one or more programming languages, and can be executed completely on a user device, partially on a user device, as a stand-alone software package, partially on a user device and partially on a remote device, or completely on a remote device.

[0119] The technical features of the above-described embodiments can be combined in any manner. To make the description concise, all possible combinations of the technical features in the above-described embodiments are not described, however, as long as the combinations of the technical features do not contradict each other, they should be considered within the scope of the present application.

[0120] The above-described embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the patent. It should be pointed out that, for ordinary skilled persons in the art, several modifications and improvements can be made without departing from the concept of the present application, and these are within the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for diagnosing yaw faults in wind turbines based on the abrupt coupling of three-dimensional data, characterized in that, include: Acquire 3D yaw monitoring parameters within a preset time period, including yaw rotation rate, yaw motor current, and yaw pressure pulsation. The three-dimensional anomaly value interval is determined based on the standard deviation of the rate of change of each yaw monitoring parameter, and the abnormal value of each yaw monitoring parameter is determined based on the values ​​of adjacent monitoring times in the three-dimensional anomaly value interval. The abnormal value is determined to be mutated data according to a preset mutation threshold, and the ternary abnormal values ​​at the same time are coupled according to the determination result to obtain the coupled target abnormal status code. Obtain the mapping relationship between abnormal status codes, diagnostic criteria, and fault types, and determine the corresponding target diagnostic criteria and target fault type from the mapping relationship based on the target abnormal status code.

2. The method for diagnosing yaw faults of wind turbines based on the abrupt coupling of three-dimensional data as described in claim 1, characterized in that, The determination of the ternary anomaly value range based on the standard deviation of the rate of change of each yaw monitoring parameter includes: Calculate the rate of change of each yaw monitoring parameter between the current time and the previous time. Calculate the standard deviation of the rate of change of each yaw monitoring parameter from the start time to the current time; Within a preset time period, in response to the absolute value of the rate of change being greater than three times the standard deviation of the corresponding yaw monitoring parameter, the multivariate yaw monitoring parameter at the corresponding time is added to the ternary abnormal value range.

3. The wind turbine yaw fault diagnosis method based on three-element data mutation coupling according to claim 2, characterized in that, The determination of the abnormal values ​​for each yaw monitoring parameter based on the values ​​at adjacent monitoring times within the three-dimensional abnormal value interval includes: Determine whether the average value of each yaw monitoring parameter at two adjacent monitoring times is greater than a preset average value, or whether the difference between the values ​​at two adjacent monitoring times is greater than a preset difference value, within the three-dimensional abnormal value range. If so, the monitoring value at the current monitoring time will be taken as the abnormal value of the corresponding yaw monitoring parameter.

4. The wind turbine yaw fault diagnosis method based on three-element data mutation coupling according to claim 3, characterized in that, The process of coupling the ternary anomaly values ​​at the same time based on the judgment result to obtain the coupled target anomaly status code includes: For the abnormal values, the mutated data is marked with a first identifier, and the non-mutated data is marked with a second identifier. The target abnormal status code is determined based on the first identifier and the second identifier.

5. The method for diagnosing yaw faults of wind turbines based on the abrupt coupling of three-dimensional data as described in claim 1, characterized in that, The mapping relationship between exception status codes and fault types includes: When the yaw pressure pulsation is abrupt, and the yaw rotation rate and the yaw motor current are abrupt, the fault type is hydraulic system failure or motor system failure. When the yaw pressure pulsation is non-abrupt data, and the yaw rotation rate and the yaw motor current are abrupt data, the fault type is yaw gear tooth breakage or soft starter failure. When the yaw pressure pulsation is abrupt, the yaw rotation rate is non-abrupt, and the yaw motor current is abrupt, the fault type is yaw resonance.

6. The method for diagnosing yaw faults of wind turbines based on the abrupt coupling of three-dimensional data as described in claim 5, characterized in that, When the target fault type corresponding to the target abnormal status code is not limited to one, the method further includes: The order in which the yaw monitoring parameters abruptly change is determined based on the abnormal values ​​at adjacent monitoring times; If the yaw pressure pulsation is the first to change abruptly, and both the yaw rotation rate and the yaw motor current are abruptly changed data, the fault type is hydraulic system failure. If the motor current is the first to experience a sudden change, and both the yaw rotation rate and the yaw motor current are sudden data, the fault type is motor system failure. If the yaw rotation rate is the first to experience a sudden change, and the yaw pressure pulsation is a non-sudden change, while the yaw motor current is a sudden change, then the fault type is a broken yaw gear tooth.

7. A wind turbine yaw fault diagnosis system based on three-dimensional data mutation coupling, characterized in that, include: Acquisition module: used to acquire three-dimensional yaw monitoring parameters within a preset time period, including yaw rotation rate, yaw motor current and yaw pressure pulsation; Anomaly module: used to determine the three-dimensional anomaly value range based on the standard deviation of the rate of change of each yaw monitoring parameter, and to determine the abnormal value of each yaw monitoring parameter based on the values ​​of adjacent monitoring times in the three-dimensional anomaly value range. Status code module: used to determine whether the abnormal value is mutated data according to a preset mutation threshold, and to couple the ternary abnormal values ​​at the same time according to the judgment result to obtain the coupled target abnormal status code. Diagnostic module: Used to obtain the mapping relationship between abnormal status codes, diagnostic criteria and fault types, and to determine the corresponding target diagnostic criteria and target fault type from the mapping relationship based on the target abnormal status code.

8. An electronic device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements a wind turbine yaw fault diagnosis method based on three-element data mutation coupling as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements a wind turbine yaw fault diagnosis method based on the abrupt coupling of three-dimensional data as described in any one of claims 1 to 6.

Images